© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 94517
    Prev
    Next
    INDEX
    Explanations

    references to cinematic experiences and adaptations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    covering
    -0.06
    lasses
    -0.06
    leur
    -0.06
    emmel
    -0.06
     Deadline
    -0.06
    Tube
    -0.06
    ç«
    -0.06
    ÏĦι
    -0.06
    Track
    -0.06
    ega
    -0.06
    POSITIVE LOGITS
     straight
    0.08
    straight
    0.08
     Straight
    0.08
    Straight
    0.07
    dream
    0.07
     movie
    0.07
     textbook
    0.07
    aus
    0.07
    iki
    0.07
     alien
    0.06
    Activations Density 0.077%

    No Known Activations